MLP Model for Emotion Recognition using Acoustic Features
Journal: International Journal of Emerging Trends in Engineering Research (IJETER) (Vol.8, No. 5)Publication Date: 2019-10-15
Authors : Suhail MSK GunaVeerendra Kumar J Mahesh Varma U Hari Kiran Vege; Swarna Kuchibhotla;
Page : 1702-1708
Keywords : Dataset fusion; MLP classifier; RAVDESS; TESS;
Abstract
Emotion recognition is an important topic of research lately. There are already a few methods that can predict emotion but, in this paper, we im to make a unique model that is not only lightweight but also fast and accurate. We are currently focussing on predicting 4 emotions like angry, sad, neutral and happy through frequencyanalysis. To achieve this, we first needto extract7 features including 195 sub-features from an audio file. The features like MFCC, Root mean square, Spectral contrast, Tonnetz, Zero-crossing rate, Mel spectrogram frequency and Chroma combined are useful in determining emotion from the audio frequencies accurately. We have trained the model using RAVDESS and TESS which are both open source databases for audio emotions. We made an intelligent python program that can analyze the frequency pattern of each emotion using MLP classifier and predict the emotion with an accuracy of 83%.Moreover, we can predict emotion either from a file or from the microphone instantly.
Other Latest Articles
- ડીસાના ઐતિહાસિક હિન્દુ સ્થાપત્યો
- રતિદાસ કાલિદાસ રાવલ : એક સ્વાતંત્ર્ય સેનાની
- Decision Support System for Detection of False Agricultural Insurance Claims using Genetic Support Vector Machines
- સ્વામી વિવેકાનંદનું અમેરિકાગમન
- Mparison of Accuracy Level of Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) Algorithms in Predicting Heart Disease
Last modified: 2020-06-15 16:27:22